metadata

library_name: transformers
language:
  - en
license: apache-2.0
base_model: google/bert_uncased_L-4_H-512_A-8
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: bert_uncased_L-4_H-512_A-8_rte
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE RTE
          type: glue
          args: rte
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.5992779783393501

bert_uncased_L-4_H-512_A-8_rte

This model is a fine-tuned version of google/bert_uncased_L-4_H-512_A-8 on the GLUE RTE dataset. It achieves the following results on the evaluation set:

Loss: 0.6563
Accuracy: 0.5993

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 256
eval_batch_size: 256
seed: 10
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6945	1.0	10	0.6783	0.5451
0.6527	2.0	20	0.6641	0.5884
0.6024	3.0	30	0.6563	0.5993
0.528	4.0	40	0.6870	0.6173
0.4528	5.0	50	0.7337	0.6173
0.3851	6.0	60	0.7501	0.6173
0.3052	7.0	70	0.8064	0.6318
0.2478	8.0	80	0.9153	0.5993

Framework versions

Transformers 4.46.3
Pytorch 2.2.1+cu118
Datasets 2.17.0
Tokenizers 0.20.3